CFD and Machine Learning-Based Optimization of Structured Packing Geometry for Falling Film Flow

IFP Energies nouvelles - Lyon; Solaize; On-site; EUR 7,800 - 11,000; Full time

Benefits offered by this job

Remunerated internship

Job summary

IFPEN is seeking a motivated intern to work on CFD and machine learning-based optimization of structured packing geometry for falling film flow. The internship involves using validated multiphase CFD results as training data to build ML surrogates predicting wetted area and mass transfer from geometry and fluid properties.

Responsibilities include data preprocessing, model benchmarking, and exploring packing geometry optimization.

Qualifications

• Strong foundation in machine learning.
• Solid understanding of fluid mechanics/physics.
• Knowledge of chemical engineering and CFD is a plus.
• Programming skills: Python (scikit-learn, pandas, TensorFlow/PyTorch).

Responsibilities

• Literature review, selection of data, and pre-processing of CFD results.
• ML surrogate model for film flow and mass transfer.
• Benchmark against classical film and mass transfer models and integral correlations.
• Use the model to explore/optimize packing geometry.

Skills

Machine learning

Fluid mechanics

CFD knowledge

Education

Master’s degree in Applied Mathematics / Engineering

Tools

OpenFOAM

Python (scikit-learn, pandas)

TensorFlow/PyTorch

Job description

CFD and Machine Learning-Based Optimization of Structured Packing
Geometry for Falling Film Flow

IFPEN is a major player in the triple energy, ecological, and digital transition by offering differentiating technological solutions in response to societal and industrial challenges of energy and climate.

Falling liquid films appear in many industrial mass and heat transfer processes. In absorption columns (e.g. CO2 capture), the liquid flows as a film over complex surfaces (e.g. structured packings), where the geometry strongly influences flow behavior, gas-liquid contact performance, and thus process efficiency.

Understanding these flows is a key issue to design and optimize different systems, and an accurate prediction of fluid behaviour and mass transfer characteristics is highly desirable. However, experiments are exceptionally hard to perform at the relevant scales. Simplified CFD models exist but aren’t necessarily valid at the local scale, while more accurate multiphase CFD simulations (VOF, CHNS, etc.) can capture local physics accurately but are very computationally expensive.

Description :

The objective of this internship is to use existing validated multiphase CFD simulation results (10-100 cases of liquid film flow over packing geometries) as training data for a machine learning model that predicts flow and mass-transfer behaviour (wetted area, mass transfer coefficient, etc.) directly from geometric parameters and fluid properties.

Internship objectives:

• Literature review, selection of data, and pre-processing of CFD results
• ML surrogate model for film flow and mass transfer
• Benchmark against classical film and mass transfer models and integral correlations
• Use the model to explore/optimize packing geometry

Required profile :

We seek a candidate pursuing a Master’s or Engineering degree in Applied Mathematics, Artificial Intelligence, Data Science, Computational Physics, Mechanical or Chemical Engineering, or related fields.

• Technical skills: Strong foundation in machine learning. Solid understanding of fluid mechanics/physics. Knowledge of chemical engineering and CFD is a plus.
• Programming skills: Experience with Python (scikit-learn, pandas, TensorFlow/PyTorch). Familiarity with OpenFOAM is a plus.
• Soft skill and languages: Fluent English, autonomy, scientific curiosity, and critical thinking.

Additional information :

Duration of the internship: 6 months Period: February-November 2027
Workplace: IFPEN Solaize (20km south of Lyon)
Transport: A personal means of transportation is recommended but public transport is available.
Remunerated internship